© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 22-TRANSCODER-HP
    7. 113068
    Prev
    Next
    INDEX
    Explanations

    Technical documentation/code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    bis
    -0.30
    zas
    -0.29
    æĬĬæĪij
    -0.26
    cms
    -0.26
    ë°ľ
    -0.25
    zee
    -0.25
    ieties
    -0.24
    iber
    -0.24
    æĪijçĪ¸
    -0.24
    ieux
    -0.24
    POSITIVE LOGITS
     ad
    0.30
    alon
    0.27
     den
    0.27
     de
    0.27
     orig
    0.26
    æĭħ
    0.26
    alc
    0.26
    are
    0.26
     se
    0.26
     com
    0.25
    Activations Density 0.004%

    No Known Activations